GritLM-7B / dataset_num_samples.json
Muennighoff's picture
Upload folder using huggingface_hub
4d093c0 verified
{"tuluv2.jsonl": 320860, "e5_train_ds_msmarco-doc_format.jsonl": 71564, "e5_train_ds_gpt4-retrieval_format.jsonl": 166602, "e5_train_ds_nq_format.jsonl": 71408, "e5_train_ds_s2orc_format.jsonl": 80000, "e5_train_ds_t2ranking_format.jsonl": 112335, "e5_train_ds_squad_format.jsonl": 87599, "e5_train_ds_gpt4-bitext_format.jsonl": 89324, "e5_train_ds_quora_format.jsonl": 14926, "e5_train_ds_gpt4-sts_format.jsonl": 98626, "e5_train_ds_fever_format.jsonl": 71257, "e5_train_ds_mrtydi_format.jsonl": 48729, "e5_train_ds_miracl_format.jsonl": 40203, "e5_train_ds_trivia_format.jsonl": 60296, "e5_train_ds_gpt4-p2p_format.jsonl": 16842, "e5_train_ds_msmarco_format.jsonl": 244582, "e5_train_ds_hotpotqa_format.jsonl": 68659, "e5_train_ds_eli5_format.jsonl": 50293, "e5_train_ds_nli_format.jsonl": 275601, "e5_train_ds_gpt4-s2s_format.jsonl": 13481, "e5_train_ds_gpt4-p2s_format.jsonl": 121878, "e5_train_ds_dureader_format.jsonl": 86395}